Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Customize, Emotional Control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cols
    0.40
    ín
    0.39
     retribution
    0.39
    ologia
    0.39
    取的
    0.39
    ewall
    0.39
     cure
    0.39
    ’
    0.38
     콜
    0.37
    eres
    0.37
    POSITIVE LOGITS
     Freem
    0.43
    NewLabel
    0.39
     izgleda
    0.39
     बे
    0.39
    Sounds
    0.39
    SHADER
    0.39
    щенко
    0.38
     офи
    0.38
    󠁬
    0.37
    ()):
    0.37
    Act Density 0.000%

    No Known Activations